arch/tile: allow nonatomic stores to interoperate with fast atomic syscalls

This semantic was already true for atomic operations within the kernel,
and this change makes it true for the fast atomic syscalls (__NR_cmpxchg
and __NR_atomic_update) as well.  Previously, user-space had to use
the fast atomic syscalls exclusively to update memory, since raw stores
could lose a race with the atomic update code even when the atomic update
hadn't actually modified the value.

With this change, we no longer write back the value to memory if it
hasn't changed.  This allows certain types of idioms in user space to
work as expected, e.g. "atomic exchange" to acquire a spinlock, followed
by a raw store of zero to release the lock.

Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index 82f64cc6365..24448734f6f 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -59,7 +59,7 @@
  * bad kernel addresses).
  *
  * Note that if the value we would store is the same as what we
- * loaded, we bypass the load.  Other platforms with true atomics can
+ * loaded, we bypass the store.  Other platforms with true atomics can
  * make the guarantee that a non-atomic __clear_bit(), for example,
  * can safely race with an atomic test_and_set_bit(); this example is
  * from bit_spinlock.h in slub_lock() / slub_unlock().  We can't do